Fruit recognition system / Nurul Husna Mohd Hofni

Nurul Husna, Mohd Hofni (2011) Fruit recognition system / Nurul Husna Mohd Hofni. Degree thesis, Universiti Teknologi MARA Cawangan Perak.

Download

[thumbnail of 34265.pdf] Text
34265.pdf

Download (127kB)

Abstract

Recognition system becomes an important field of computer science due to rapid development of technology. Several fruit recognitions have been developed to fulfill the needs on research based on image processing. Fruits can be recognized based on their basic features such as shape, color and texture. However, using color features and shape features analysis methods are still not robust and effective enough to identify and distinguish fruit images. A Fruit Recognition System has been proposed, which combines four features analysis methods which are edge-based, color-based, shape-based and size-based in order to increase accuracy of recognition. The objective of this project is to develop an automatic system for fruits recognition. Proposed method recognized fruit images based on obtained features. The recognition was done by calculating the properties of the shape of objects such as diameter, area, and also perimeter. Mean score from these three properties was calculated to recognize the fruits types. Then, the color of an image was extracted to find its dominant color by using RGB and HSV color space. 60 samples of fruits images from five different types of fruits were used to confirm the effectiveness of the proposed approach. Based on experimental results, approximately 96% of the fruits were recognized successfully. Future work could be directed to recognize more types of fruits images. Besides, the texture based analysis technique could be implemented with the existing four features analysis in order to obtain more accurate results for fruits recognition. This system can be applied in a variety fields such as educational, and image retrieval.

Metadata

Item Type: Thesis (Degree)
Creators:
Creators
Email
Nurul Husna, Mohd Hofni
2009447008
Contributors:
Contribution
Name
Email / ID Num.
Thesis advisor
Prof Madya Dr. Puteri Nor Hashimah, Megat Abdul Rahman
UNSPECIFIED
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Computer software > Application software
Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Algorithms
Q Science > QA Mathematics > Philosophy > Mathematical logic > Constructive mathematics > Algorithms
Divisions: Universiti Teknologi MARA, Perak > Tapah Campus > Faculty of Computer and Mathematical Sciences
Item ID: 34265
Uncontrolled Keywords: image recognition system, graphical user interface, algorithm method
URI: https://ir.uitm.edu.my/id/eprint/34265

Fulltext

Fulltext is available at:
  • Bilik Koleksi Akses Terhad, PTAR Kampus Tapah, Perak
  • ID Number

    34265

    Indexing


    View in Google Scholar

    Edit Item
    Edit Item